Zero-Shot LLMs for Named Entity Recognition: Targeting Cardiac Function Indicators in German Clinical Texts

Large Language Models (LLMs) like ChatGPT have become increasingly prevalent. In medicine, many potential areas arise where LLMs may offer added value. Our research focuses on the use of open-source LLM alternatives like Llama 3, Gemma, Mistral, and Mixtral to extract medical parameters from German clinical texts. We concentrate on German due to an observed gap in research for non-English tasks.

To evaluate the effectiveness of open-source LLMs in extracting medical parameters from German clinical texts, specially focusing on cardiovascular function indicators from cardiac MRI reports.

We extracted 14 cardiovascular function indicators, including left and right ventricular ejection fraction (LV-EF and RV-EF), from 497 variously formulated cardiac magnetic resonance imaging (MRI) reports. Our systematic analysis involved assessing the performance of Llama 3, Gemma, Mistral, and Mixtral models in terms of right annotation and named entity recognition (NER) accuracy.

The analysis confirms strong performance with up to 95.4% right annotation and 99.8% NER accuracy across different architectures, despite the fact that these models were not explicitly fine-tuned for data extraction and the German language.

The results strongly recommend using open-source LLMs for extracting medical parameters from clinical texts, including those in German, due to their high accuracy and effectiveness even without specific fine-tuning.